Case Study on Applying a Deep Learning-Based 3D Trace Regularization Method to OBN Field Data Acquired in the Pohang Basin,  South Korea

Gahyeon Lee; Zeu Yeeh; Soon Jee Seol; Joongmoo Byun1

doi:10.7582/GGE.2025.28.4.142

All Issue

2025 Vol.28, Issue 4 Preview Page Next Page

Research Article

Case Study on Applying a Deep Learning-Based 3D Trace Regularization Method to OBN Field Data Acquired in the Pohang Basin, South Korea 포항 영일만 OBN 자료의 딥러닝 기반 3차원 정규화 기법 적용 사례 연구

30 November 2025. pp. 142-155

PDF XML

Abstract

Seismic data regularization is a critical step that improves the quality of subsequent data processing. We present a case study applying a deep learning (DL)–based regularization method using Delaunay tessellation proposed by Yeeh (2024) to small-scale, 3D ocean bottom node (OBN) data acquired from irregularly positioned sources in Yeongil Bay, Pohang. The DL model for regularization was trained solely on the preprocessed field data. We describe the data preprocessing and training data selection strategies used to enhance model performance. The trained DL model regularized the irregularly located source positions to a 10-meter spacing, which is denser than the originally acquired spacing of 25 -50 meters. Except for a few receiver nodes lacking nearby sources in near-offset regions where the curvature of arrival times varied, the main signals were well predicted. The results also effectively suppressed random noise. Because this method enables both the interpolation and regularization of irregularly acquired 3D seismic data using only field data, it is highly adaptable for future geophysical applications.

Keywords

Regularization

Interpolation

Deep learning

Ocean Bottom Node (OBN)

3D Seismic Data

탄성파 탐사 자료에서 정규화(regularization)는 이후의 자료처리 수행을 수월하게 하는 매우 중요한 과정이다. 이 연구에서는 송신원들이 다소 불규칙하게 취득된 포항 영일만의 소규모 3차원 OBN (Ocean Bottom Node) 자료에 Yeeh (2024)의 델로네이 공간분할을 이용한 딥러닝 기반 정규화 기법을 적용한 사례를 보여준다. 중합전(pre-stack) 현장 자료의 특성 분석 및 전처리를 수행한 후 이 자료만으로 정규화 딥러닝 모델을 학습시켰으며 성능 향상을 위한 자료의 전처리 방법 및 학습 자료 선별 과정을 제시하였다. 학습된 딥러닝 모델로 원자료의 측선 간격인 약 25 ~ 50 m 보다 조밀한 10 m 간격으로 정규화를 수행하였으며, 그 결과 도착 시간의 곡률이 변하는 근거리 오프셋(near offset) 구간에 송신원이 전혀 없는 일부 수신 노드 자료의 경우를 제외하고는 주 신호들이 대부분 잘 예측되며 전체적으로 무작위 잡음이 억제된 정규화 결과를 얻었다. 이 방법은 현장자료 자체만을 이용하여 불규칙하게 위치한 3차원 탐사자료의 내삽과 정규화를 동시에 수행할 수 있어 추후에도 많은 활용이 가능할 것이다.

키워드

정규화

내삽

딥러닝

OBN

3차원 탄성파 자료

References

Abma, R. and Kabir, N., 2006, 3D interpolation of irregular data with a POCS algorithm, Geophysics, 71(6), E91–E97.

10.1190/1.2356088

Greiner, T. A. L., Lie, J. E., Kolbjørnsen, O., Evensen, A. K., Nilsen, E. H., Zhao, H., Demyanov, V., and Gelius, L. J., 2022, Unsupervised deep learning with higher-order total-variation regularization for multidimensional seismic data reconstruction, Geophysics, 87(2), V59–V73.

10.1190/geo2021-0099.1

Kaur, H., Pham, N., and Fomel, S. (2021). Seismic data interpolation using deep learning with generative adversarial networks, Geophysical Prospecting, 69(2), 307-326.

10.1111/1365-2478.13055

Kwon, Y. K., 2018, Demonstration-scale offshore CO₂ storage project in the Pohang Basin, Korea, The Journal of Engineering Geology, 28(2), 133-160 (in Korean with English abstract).

10.9720/KSEG.2018.2.133

Lee, C. B., Kim, T. K., and Park, D. W., 2009, Geology and geochemistry of volcanic and sedimentary rocks from deep borehole in the Heunghae area, North Kyungsang Province, The Journal of Engineering Geology, 19(4), 459-474 (in Korean with English abstract).

Lee, D. T. and Schachter, B. J.,1980, Two algorithms for constructing a Delaunay triangulation, International Journal of Computer & Information Sciences, 9(3), 219-242.

10.1007/BF00977785

Lee, M. O., Kim, J. K., and Kim, B. K., 2023, Marine Environmental Characteristics of Yeongil Bay, Korea, Journal of the Korean Society for Marine Environment & Energy, 26(1), 11-33 (in Korean with English abstract).

10.7846/JKOSMEE.2023.26.1.11

Liu, B. and Sacchi, M. D., 2004, Minimum weighted norm interpolation of seismic records, Geophysics, 69(6), 1560–1568.

10.1190/1.1836829

Mo, T., Song, J., Li, Z., and Wang, B, 2025, Deep learning-based off-the-grid seismic data reconstruction and regularization: Preliminary research, Geophysics, 90(1), V1-V12.

10.1190/geo2023-0666.1

Möbius, A. F., 1827, Der Barycentrische Calcul: Ein Neues Hülfsmittel zur Analytischen Behandlung der Geometrie, Dargestellt und Insbesondere auf Die Bildung Neuer Classen von Aufgaben und Die Entwickelung Mehrerer Eigenschaften der Kegelschnitte Angewendet, JA Barth.

National Geographic Information Institute (NGII), 2024, https://map.ngii.go.kr/mi/dwldSvc/mapDwldSvcForm.do (June 30, 2025 Accessed)

National Geographic Information Institute (NGII), 2025, https://map.ngii.go.kr/ms/map/nlipCASImgMap.do (July 20, 2025 Accessed)

Noh, J. H., 1994, Stratigraphy, lithology and diagenetic mineral facies of the Tertiary Yeonil Group, The Korean Journal of Petroleum Geology, 2(2), 91-99 (in Korean with English abstract).

Park, M. H., Lee, C. S., Kim, B. Y., Kim, J. H., Kim, K. J., and Shinn, Y. J., 2018, Preliminary results of the pre-injection monitoring survey at an offshore CO₂ injection site in the Yeongil Bay, The Journal of Engineering Geology, 28(2), 247-258 (in Korean with English abstract).

Park, S. E., Li, X., Kim, B. Y., Oh, J. W., Min, D. J., and Kim, H. S., 2021, Seismic imaging of ocean-bottom seismic data for finding a carbon capture and storage site: Two-dimensional reverse-time migration of ocean-bottom seismic data acquired in the Pohang Basin, South Korea, Geophysics and Geophysical Exploration, 24(3), 78-88 (in Korean with English abstract).

10.7582/GGE.2021.24.3.078

Saad, O. M., Fomel, S., Abma, R., and Chen, Y., 2023, Unsupervised deep learning for 3D interpolation of highly incomplete data, Geophysics, 88(1), WA189-WA200.

10.1190/geo2022-0232.1

Seo, Y. K. and Kim, D. C., 2000, Acoustic property of sandy sediment in the korea strait using sediment sound velocimeter, The Journal of the Acoustical Society of Korea, 19(3), 77-85 (in Korean with English abstract).

Shinn, Y. J., Kwon, Y. K., Yoon, J. R., Kim, B. Y., and Cheong, S., 2018, Result of CO₂ geological storage site survey for small-scale demonstration in Pohang Basin, Yeongil Bay, SE Korea, The Journal of Engineering Geology, 28(2), 161-174 (in Korean with English abstract).

10.9720/KSEG.2018.2.161

Wang, B., Zhang, N., Lu, W., and Wang, J., 2019, Deep-learning-based seismic data interpolation: A preliminary result, Geophysics, 84(1), V11-V20.

10.1190/geo2017-0495.1

Wang, Y., Wang, B., Tu, N., and Geng, J., 2020, Seismic trace interpolation for irregularly spatial sampled data using convolutional autoencoder, Geophysics, 85(2), V119-V130.

10.1190/geo2018-0699.1

Xu, S., Zhang, Y., and Lambaré, G., 2010, Antileakage Fourier transform for seismic data regularization in higher dimensions, Geophysics, 75(6), WB113-WB120.

10.1190/1.3507248

Yeeh, Z., 2024, Three-Dimensional Seismic Trace Regularization Using Machine Learning with Delaunay Tessellation, Ph.D. thesis, Hanyang University. 108p.

Information

Publisher :Korean Society of Earth and Exploration Geophysicists
Publisher(Ko) :한국지구물리물리탐사학회
Journal Title :Geophysics and Geophysical Exploration
Journal Title(Ko) :지구물리와 물리탐사
Volume : 28
No :4
Pages :142-155
Received Date : 2025-08-13
Revised Date : 2025-09-18
Accepted Date : 2025-11-03
DOI :https://doi.org/10.7582/GGE.2025.28.4.142

Geophysics and Geophysical Exploration ISSN:1229-1064(Print) 2384-051X(Online) 지구물리와 물리탐사

All Issue